comparison cpo_galaxy_tree.py @ 7:4d2777aa99db draft

planemo upload

6:cabceaa239e4

#$ -S /home/jjjjia/.conda/envs/py36/bin/python
#$ -V             # Pass environment variables to the job
#$ -N CPO_pipeline    # Replace with a more specific job name
#$ -wd /home/jjjjia/testCases           # Use the current working dir
#$ -pe smp 8      # Parallel Environment (how many cores)
#$ -l h_vmem=11G  # Memory (RAM) allocation *per core*
#$ -e ./logs/$JOB_ID.err
#$ -o ./logs/$JOB_ID.log
#$ -m ea
#$ -M [e-mail]

#~/scripts/pipeline.py -i BC11-Kpn005_S2 -f /data/jjjjia/R1/BC11-Kpn005_S2_L001_R1_001.fastq.gz -r /data/jjjjia/R2/BC11-Kpn005_S2_L001_R2_001.fastq.gz -o pipelineResultsQsub -e "Klebsiella pneumoniae" 

import subprocess
import pandas
import optparse
import os
import datetime
import sys
import time
import urllib.request
import gzip
import collections
import json
import numpy
import ete3 as e


#parses some parameters
parser = optparse.OptionParser("Usage: %prog [options] arg1 arg2 ...")
parser.add_option("-t", "--tree", dest="treePath", type="string", default="./pipelineTest/tree.txt", help="identifier of the isolate")    

        self.NearestReference = ""

#endregion

#region useful functions
def read(path):
    return [line.rstrip('\n') for line in open(path)]
def execute(command):
    process = subprocess.Popen(command, shell=False, cwd=curDir, universal_newlines=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)

    # Poll process for new output until finished
    while True:
        nextline = process.stdout.readline()

    if (exitCode == 0):
        return output
    else:
        raise subprocess.CalledProcessError(exitCode, command)
def httpGetFile(url, filepath=""):
    if (filepath == ""):
        return urllib.request.urlretrieve(url)
    else:
        urllib.request.urlretrieve(url, filepath)
        return True
def gunzip(inputpath="", outputpath=""):
    if (outputpath == ""):
        with gzip.open(inputpath, 'rb') as f:
            gzContent = f.read()
        return gzContent
    else:
        with gzip.open(inputpath, 'rb') as f:
            gzContent = f.read()
        with open(outputpath, 'wb') as out:
            out.write(gzContent)
        return True
def addFace(name):
    #if its the reference branch, populate the faces with column headers
    face = e.faces.TextFace(name,fsize=10,tight_text=True)
    face.border.margin = 5
    face.margin_right = 5
    face.margin_left = 5

7:4d2777aa99db

#$ -S /home/jjjjia/.conda/envs/py36/bin/python
#$ -V             # Pass environment variables to the job
#$ -N CPO_pipeline    # Replace with a more specific job name
#$ -wd /home/jjjjia/testCases           # Use the current working dir
#$ -pe smp 1      # Parallel Environment (how many cores)
#$ -l h_vmem=11G  # Memory (RAM) allocation *per core*
#$ -e ./logs/$JOB_ID.err
#$ -o ./logs/$JOB_ID.log
#$ -m ea
#$ -M [e-mail]

#   >python cpo_galaxy_tree.py -t /path/to/tree.ph -d /path/to/distance/matrix -m /path/to/metadata

#	<requirements>
#		<requirement type="package" version="0.23.4">pandas</requirement>
#		<requirement type="package" version="3.6">python</requirement>
#       <requirement type="package" version="3.1.1">ete3</requirement>
#		<requirement type="package" version="5.9.3">pyqt</requirement>
#  </requirements>

import subprocess
import pandas #conda pandas
import optparse
import os
import datetime
import sys
import time
import urllib.request
import gzip
import collections
import json
import numpy #conda numpy
import ete3 as e #conda ete3 3.1.1**** >requires pyqt5


#parses some parameters
parser = optparse.OptionParser("Usage: %prog [options] arg1 arg2 ...")
parser.add_option("-t", "--tree", dest="treePath", type="string", default="./pipelineTest/tree.txt", help="identifier of the isolate")    

        self.NearestReference = ""

#endregion

#region useful functions
def read(path): #read in a text file to a list
    return [line.rstrip('\n') for line in open(path)]
def execute(command): #subprocess.popen call bash command
    process = subprocess.Popen(command, shell=False, cwd=curDir, universal_newlines=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)

    # Poll process for new output until finished
    while True:
        nextline = process.stdout.readline()

    if (exitCode == 0):
        return output
    else:
        raise subprocess.CalledProcessError(exitCode, command)
def httpGetFile(url, filepath=""): #download a file from the web
    if (filepath == ""):
        return urllib.request.urlretrieve(url)
    else:
        urllib.request.urlretrieve(url, filepath)
        return True
def gunzip(inputpath="", outputpath=""): #gunzip
    if (outputpath == ""):
        with gzip.open(inputpath, 'rb') as f:
            gzContent = f.read()
        return gzContent
    else:
        with gzip.open(inputpath, 'rb') as f:
            gzContent = f.read()
        with open(outputpath, 'wb') as out:
            out.write(gzContent)
        return True
def addFace(name): #function to add a facet to a tree
    #if its the reference branch, populate the faces with column headers
    face = e.faces.TextFace(name,fsize=10,tight_text=True)
    face.border.margin = 5
    face.margin_right = 5
    face.margin_left = 5